Abstract
Motion stereo refers here to finding camera motion from two TV images taken with a moving camera. A wide-angle motion stereo is described to aid navigation of autonomous vehicles. The approach uses structural information observed in a scene as features to be matched in the two images. The matching is done in the three-dimensional (3-D) world using range information obtained by inverse perspective transformation. Some experimental results are shown.
Original language | English (US) |
---|---|
Title of host publication | Proceedings - International Conference on Pattern Recognition |
Publisher | IEEE |
Pages | 165-168 |
Number of pages | 4 |
ISBN (Print) | 0818607424 |
State | Published - Dec 1 1986 |
Publication series
Name | Proceedings - International Conference on Pattern Recognition |
---|
Fingerprint
ASJC Scopus subject areas
- Engineering(all)
Cite this
MOTION STEREO FOR NAVIGATION OF AUTONOMOUS VEHICLES IN MAN-MADE ENVIRONMENTS. / Tsukiyama, Toshifumi; Huang, Thomas S.
Proceedings - International Conference on Pattern Recognition. IEEE, 1986. p. 165-168 (Proceedings - International Conference on Pattern Recognition).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - MOTION STEREO FOR NAVIGATION OF AUTONOMOUS VEHICLES IN MAN-MADE ENVIRONMENTS.
AU - Tsukiyama, Toshifumi
AU - Huang, Thomas S
PY - 1986/12/1
Y1 - 1986/12/1
N2 - Motion stereo refers here to finding camera motion from two TV images taken with a moving camera. A wide-angle motion stereo is described to aid navigation of autonomous vehicles. The approach uses structural information observed in a scene as features to be matched in the two images. The matching is done in the three-dimensional (3-D) world using range information obtained by inverse perspective transformation. Some experimental results are shown.
AB - Motion stereo refers here to finding camera motion from two TV images taken with a moving camera. A wide-angle motion stereo is described to aid navigation of autonomous vehicles. The approach uses structural information observed in a scene as features to be matched in the two images. The matching is done in the three-dimensional (3-D) world using range information obtained by inverse perspective transformation. Some experimental results are shown.
UR - http://www.scopus.com/inward/record.url?scp=0023027293&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0023027293&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:0023027293
SN - 0818607424
T3 - Proceedings - International Conference on Pattern Recognition
SP - 165
EP - 168
BT - Proceedings - International Conference on Pattern Recognition
PB - IEEE
ER -